© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 63794
    Prev
    Next
    INDEX
    Explanations

    Variable/unrelated themes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shr
    -0.29
    olle
    -0.29
    (async
    -0.29
    é¥
    -0.27
    å¼Ĥ
    -0.26
    orge
    -0.26
    uest
    -0.26
    å¾Ĺ罪
    -0.25
    orb
    -0.25
    é¹Ĭ
    -0.24
    POSITIVE LOGITS
    åĴĮæĶ¯æĮģ
    0.27
    UPDATED
    0.26
    -Up
    0.25
    LEY
    0.25
    anga
    0.24
    ÑģÑĮ
    0.24
    ateral
    0.24
    ismic
    0.23
    级以ä¸Ĭ
    0.23
    emade
    0.23
    Activations Density 0.439%

    No Known Activations